摘要
软件衰退现象,即软件系统随时间而出现的状态退化和性能降低,乃至系统崩溃的现象,是影响系统可靠性的一个重要因素。为了减缓软件衰退所带来的危害,软件抗衰技术被提了出来。
目前有两种最基本的软件抗衰策略——基于时间的抗衰策略和基于测量的抗衰策略。本文围绕基于测量的软件抗衰策略,结合遗传算法和神经网络对定期监测和收集到的系统性能参数进行分析,预测资源消耗和软件衰退的趋势,在系统负载过重时采取必要的应对措施。
本文首先对遗传算法和神经网络的优缺点进行分析,然后将这两种算法结合起来,使得新的结合算法能够充分利用两者的优点,既有神经网络的学习能力和鲁棒性,又有遗传算法的全局随机搜索能力。同时,本文对基本算法做了改进,对遗传算法的步骤、编码方式、参数的选取以及适应度函数的定义按照本文的需求进行设计,在对BP网络进行训练时用多种不同的学习算法做对比,选取预测效果好的方法进行实验预测。
在仿真实验中,文章给出第七天的预测值,并和实际值进行比较,说明本文算法的可行性,然后对未来的数据进行预测。最后本文对比单独用遗传算法或神经网络进行仿真实验的实验结果,表明本文算法的在预测合格率方面具有较大的优越性。
A common phenomenon which called "software aging" means the software systemdegrades with time. It always makes important influence to the system. In order tocounteract software aging, a proactive technique called "software rejuvenation" has beenproposed.
Now there are two most popular software rejuvenation strategies, the time-basedstrategy and the measurement-based strategy. This paper discusses measurement-basedsoftware rejuvenation strategy, combined with Genetic Algorithms and neutral networkmethods to analyze the parameters of system performance which are monitored andcolleted periodically. In conclusion, it predicts resource consumption and the trend ofsoftware aging.
This paper carried on the analysis to advantages and shortcoming of the BP neuralnetwork and the genetic algorithm, then this article combines the BP neural network andgenetic algorithms to full advantages of both which makes the new algorithms both havingthe BP neural network learning capability and robustness and the strong global searchcapability from the genetic algorithms. In the same time, some improvements have beenmade in this paper, such as the "growing up" process, the coding method, the parameterand the definition of the fitness function in the genetic algorithms. And during the trainingof the BP neural network, several learning methods have been compared.
Comparing the result of the seventh day giving by the experiments and the test, thealgorithm in this paper has been proved to be doable. And then this paper forecast the datain the further. At last the experiment results given both by the genetic algorithm and by theneural network have been compared, and algorithm in this paper has been proved to beefficient.
引文
1. Huang Y., Kintala C., Kolettis N. Software Rejuvenation: Analysis, Module and Applications. In: Proc. of FTCS-25, Pasadena, CA, 1995
2. Garg S., Moorsel A.v., Vaidyanathan K. A Methodology for Detection and Estimation of Software Aging. In: Proceedings of the 9th International Symposium on Software Reliability Engineering, Paderborn, Germany, 1998
3. Castelli V., Harper R.E., Heidelberger P. Proactive Management of Software Aging. IBM JRD. 2001
4. Garg S., Puliafito A., Telek M., Trivedi K. S.. Analysis of Preventive Maintenance in Transactions Based Software Systems. IEEE Transactions on Computers, 1998
5. Garg S., Puliafito A., Telek M., Trivedi K. S.. Analysis of Software Rejuvenation using Markov Regenerative Stochastic Petri Net. In: International Symposium on Software Reliability Engineering. ISSRE 1995
6. Garg S., Huang Y., Kintala C., Trivedi K. S.. Time and Load Based Software Rejuvenation: Policy, Evalnation and Optimality. In: First Fault Tolerance Symposium, FTS-95.1995
7. Garg S., Huang Y., Kintala C., Trivedi K. S.. Minimizing Completion Time of a Program by Checkpointing and Rejuvenation, ACMSIGMETRICS 1996
8. Pfening A., Garg S., Puliafito A., Telek M., Trivedi K. S.. Optimal Software Rejuvenation for Tolerating Software Failures. Performance Evaluation, 1996:27-28
9. Garg S., Puliafito A., Telek M., Trivedi K. S.. On the Analysis of Software Rejuvenation Policies. In: Annual Conference on Computer Assurance, June 1997
10. Vaidyanathan K., Trivedi K. S.. A Measurement-Based Model for Estimation of Software Aging in Operational Software Systems. In: International Symposium on Software Reliability Engineering, ISSRE 1999
11. Bobbio A., Sereno M., Anglano C. Fine Grained Software Degradation Models for Optimal Software Rejuvenation Policies. Performance Evaluation, 2001, 46:45-62
12. Li L., Vaidyanathan K., Trivedi K. S.. An Approach for Estimation of Software Aging in a Web Server. In: International Symposium on Software Engineering, ISESE 2002, Nara, Japan. Oct. 2002
13. A.Avritzer, E.J.Weyuker. Monitor smoothly degrading systems for increasing dependability. Empirical software Engineering. 1997(2):59-77
14. Vaidyanathan K. Proactive Management of Software System: Analysis and Implementation. Department of Electrical and Computer Engineering, 2002
15. Dohi T, Danjou T, Okamura H. Optimal software rejuvenation policy with discounting. Dependable Computing, 2001. Proceedings. 2001 Pacific Rim International Symposium 17-19 Dec. 2001:87-94
16.李正,万群丽,许满武.软件恢复技术研究.计算机科学.2003,30(8)
17. Marshall E. Fatal Error: How Patriot Overlooked a Scud. Science. Mar. 1992
18. Randall S. Sexton, Robert E. Dorsey, John D. Johnson. Optimization of Neural Networks:a Comparative Analysis of the Genetic Algorithm and Simulated Annealing. European Journal of Operational Research, 1999, 114(3):589-601
19. IBM Netfinity Director Software Rejuvenation. White Paper, IBM Corp., Research Triangle Park, N.C., Jan. 2001
20. K. Vaidyanathan, R. E. Harper, S. W. Hunter, K. S. Trived. Analysis and Implementation of Software Rejuvenation in Cluster Systems. Proceedings Joint Intelnational Conference Measurement and Modeling of Computer Systems, ACM SIGMETRICS 2001/Performance 2001, June 2001
21. K. Cassidy, K. Gross, and A. Malekpour. Advanced Pattern Recognition for Detection of Complex Software Aging in Online Transaction Processing Servers. Proc. Conf. Dependable Systems and Networks (DSN 2002), June 2002
22. Y. Hong, D. Chen, L. Li, and K.S. Trived. Closed Loop Design for Software Rejuvenation. Proc. Workshop Self-Healing, Adaptive and Self-Managed Systems (SHAMAN 2002), June 2002
23. Srinivas, M.and Patnaik, L. M., Adaptive Probabilities of Crossover and Mutation in Genetic Algorithms, IEEE Transactions on system, Man, and Cybernetics, 1994, 24(4):367-384
24. S.H.Ling, H.K.lam, H.Rleung, and Y S.Lee. Improved Genetic Algorithm for Economic Load Dispatch with Vale-Point Loadings. IEEE, 2003, 18(5):462-469
25. Fank H.F.Leng, H.K.Lam, S.H.Ling and Pete K.S.Tam. Tuning of the Structure and Parameters of Neural Network Using an Improved Genetic Algorithm. IEEE.2003, 18(5):476-482
26.董玲娇.基于遗传算法的智能控制器设计方法研究.郑州大学,2004
27.刘勇,康立山,陈毓屏.非数值并行算法(第二册)遗传算法.北京:科学出版社,1995
28.李士勇.模糊控制·神经网络和智能控制理论(第二版).哈尔滨:哈尔滨工业大学出版社,1998
29.杜永贵.GA-Fuzzy自适应控制系统.太原理工大学,1997
30.田军,寇纪淞,李敏强.遗传算法中自适应变异算子的优化.大学系统工程研究所:大连海事大学出版社,1998
31. Ilona et al. An investigation into the application of neural networks, fuzzy logic, genetic algorithms, and rough sets to automated knowledge acquisition forclassification problems. Neurocomputing, 1999, 24: 37-54.
32.李敏强,陈熙源,万德钧.遗传算法与神经网络的结合.系统工程理论与实践,1999(2):60-75.
33.舒云星,张永胜,郁可.基于遗传算法的BP网络优化研究.山东建材学院学报,2000,14(1):2224.
34.孙卫国等.基于遗传算法的神经网络为苯乙酞胺类农药构效关系建模的研究.高等学校化学学报,1998, 19(6):871.
35. Sung-Base Cho. Pattern recognition wit neural networks combined by genetic algorithm. Fuzzy Sets and Systems, 1999, 103:339-347
36.王建成,高大启,王静等.改进的遗传和BP杂交算法及神经网络经济预警系统设计.系统工程理论与实践,1998,18(4):136-141
37.郑志军,郑守淇.用基于实数编码的自适应遗传算法进化神经网络.计算机工程及应用,2000,(9):36-37
38.陈朝阳等.基于遗传算法的神经网络模型的建立.1997,16(1):60-73
39.陈允平,王旭蕊,韩宝亮.人工神经网络及其应用.北京:中国电力出版社,2002
40. Zhou Chunguang, Zhang Bing and Cheng Yanfeng. 1996. Genetic algorithm and its application in training feed forward neural Network. MINI-MICRO SYSTEMS, 17(6):54-58
41. Koza J R, Rice J P. Genetic generation of both the weights and architecture for a neural network. International Joint Conference on Neural Networks, IJCNN-91-Seattle, 1991:397-404
42. Chen Fangze and Chen Bingzhen. 1996. Training artificial neural network with extended genetic algorithms. Journal of Chemical Industry and Engineering, 47(3): 280-286
43. D. Nguyen, B. Widrow. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights, in Int. Joint Conf. Neural Networks, 1990, 3: 21-26
44.翟宜峰,刘寒冰.用遗传算法优化神经网络初始权重的方法.吉林大学学报(工学版),2003
45.王小平,曹立明.遗传算法.理论应用与软件实现.西安交通大学出版社,2002
46. H Handles, Th Rob. Feature selection for optimized skin tumor recognition using genetic algorithm.Artificial Intelligence in Medicine, 1999, 16:283-289
47. Sameh M Yamany, Kamal J Khiani. Application of neural network and genetic algorithms in the classification of endothelial cells. Pattern Recognition Letters, 1997, 18:1205-1210
48. Vittorio Maniezzo. Genetic evolution of the topology and weight distribution of neural networks. IEEE Trans. Neural Network, 1994, 5:39-53
49.张文修,梁怡.遗传算法的数学基础.西安:西安交通大学出版社,2000
50. Maclay, D., and Dorey, R. Applying genetic search techniques to drivetrain modeling. IEEE Control Systems, Special Issue on Intelligent Control, Vol. 13, No. 3, 1993: 50-55
51. Freeman, L. M., et al. Turning fuzzy logic controller using genetic algorithms aerospace applications. In Proceedings of the AAAIC'90 Conference, Dayton, Oct., 1990:351-358
52. De Jong K A. Genetic algorithms: a 25 years perspective. Computational intelligence imitating life. New York: IEEE press 1994:125-136
53.梁建辉.基于遗传算法的神经网络预测控制及应用.西安:西北工业大学出版社,2003.3
54.赵会.地区宏观经济预测中的人工神经网络模型与方法研究.大连理工大学硕士学位论文,2000
55.邵军力,张景,魏长华.人工智能基础.北京:电子工业出版社,2000
56.刘春艳.基于遗传算法-BP神经网络的主汽温控制系统的研究.太原理工大学硕士学位论文,2006.5
57.吴建生.基于遗传算法的BP神经网络气象预报建模.广西师范大学硕士研究生学位论文,2004.3
58.焦李成.神经网络系统理论.西安:西安电子科技大学出版社,1990
59.陈天平.神经网络及其在系统识别应用中的逼近问题.中国科学(A辑).1994,24(1):1-7
60.胡淼.软件衰退预测算法的研究.南京理工大学硕士学位论文,2006
61.周丽华等.基于神经网络的手写体数字识别.云南大学学报(自然科学版).1995,17(1):69-72